Merge remote-tracking branch 'refs/remotes/origin/bert' into bert

use infer lib

demo-client/src/data_pre.h

@@ -14,6 +14,7 @@
 #ifndef SERVING_DEMO_CLIENT_SRC_DATA_PRE_H_
 #define SERVING_DEMO_CLIENT_SRC_DATA_PRE_H_
 #include <sys/stat.h>
+#include <iostream>
 #include <map>
 #include <string>
 #include <vector>

demo-serving/conf/model_toolkit.prototxt

+engines {
+  name: "bert"
+  type: "FLUID_GPU_ANALYSIS_DIR"
+  reloadable_meta: "./data/model/paddle/fluid_time_file"
+  reloadable_type: "timestamp_ne"
+  model_data_path: "./data/model/paddle/fluid/bert"
+  runtime_thread_num: 0
+  batch_infer_size: 0
+  enable_batch_align: 0
+}

demo-serving/conf/service.prototxt

+services {
+  name: "BertService"
+  workflows: "workflow9"
+}

demo-serving/op/bert_service_op.cpp

@@ -137,7 +137,7 @@ int BertServiceOp::inference() {
         << " seq_len : " << out->at(0).shape[1]
         << " emb_size : " << out->at(0).shape[2];
 
-    float *out_data = reinterpret_cast<float *>out->at(0).data.data();
+    float *out_data = reinterpret_cast<float *>(out->at(0).data.data());
     for (uint32_t bi = 0; bi < batch_size; bi++) {
       BertResInstance *res_instance = res->add_instances();
       for (uint32_t si = 0; si < MAX_SEQ_LEN; si++) {
@@ -151,7 +151,7 @@ int BertServiceOp::inference() {
 #else
   LOG(INFO) << "batch_size : " << out->at(0).shape[0]
             << " emb_size : " << out->at(0).shape[1];
-  float *out_data = reinterpret_cast<float *> out->at(0).data.data();
+  float *out_data = reinterpret_cast<float *>(out->at(0).data.data());
   for (uint32_t bi = 0; bi < batch_size; bi++) {
     BertResInstance *res_instance = res->add_instances();
     for (uint32_t si = 0; si < 1; si++) {